© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 22020
    Prev
    Next
    INDEX
    Explanations

    words related to the purpose or objective of a study, project, meeting, or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases or contexts related to aims and purposes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.86
    Enlarge
    -0.73
     traces
    -0.69
    eph
    -0.68
    ashtra
    -0.68
     epile
    -0.67
    dayName
    -0.65
     Cros
    -0.64
    abytes
    -0.64
    fml
    -0.61
    POSITIVE LOGITS
    thood
    0.76
     delivering
    0.74
     inducing
    0.73
     protecting
    0.72
     preserving
    0.71
     supplying
    0.71
    ãĥĦ
    0.71
     preventing
    0.71
     course
    0.69
     persuasion
    0.69
    Activations Density 0.156%

    No Known Activations